Adding utility methods to TensorProperties

Summary:
Context: in the code we are releasing with CO3D dataset, we use  `cuda()` on TensorProperties like Pointclouds and Cameras where we recursively move batch to a GPU. It would be good to push it to a release so we don’t need to depend on the nightly build.

Additionally, I aligned the logic of `.to("cuda")` without device index to the one of `torch.Tensor` where the current device is populated to index. It should not affect any actual use cases but some tests had to be changed.

Reviewed By: bottler

Differential Revision: D29659529

fbshipit-source-id: abe58aeaca14bacc68da3e6cf5ae07df3353e3ce

tests/test_rendering_utils.py

@@ -39,7 +39,17 @@ class TestTensorProperties(TestCaseMixin, unittest.TestCase):
         example = TensorPropertiesTestClass(x=10.0, y=(100.0, 200.0))
         device = torch.device("cuda:0")
         new_example = example.to(device=device)
-        self.assertTrue(new_example.device == device)
+        self.assertEqual(new_example.device, device)
+
+        example_cpu = example.cpu()
+        self.assertEqual(example_cpu.device, torch.device("cpu"))
+
+        example_gpu = example.cuda()
+        self.assertEqual(example_gpu.device.type, "cuda")
+        self.assertIsNotNone(example_gpu.device.index)
+
+        example_gpu1 = example.cuda(1)
+        self.assertEqual(example_gpu1.device, torch.device("cuda:1"))
 
     def test_clone(self):
         # Check clone method